Accelerating materials property predictions using machine learning. Pilania, G., Wang, C., Jiang, X., Rajasekaran, S., & Ramprasad, R. Scientific Reports, 3(1):2810, September, 2013. Number: 1 Publisher: Nature Publishing Group![Accelerating materials property predictions using machine learning [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The materials discovery process can be significantly expedited and simplified if we can learn effectively from available knowledge and data. In the present contribution, we show that efficient and accurate prediction of a diverse set of properties of material systems is possible by employing machine (or statistical) learning methods trained on quantum mechanical computations in combination with the notions of chemical similarity. Using a family of one-dimensional chain systems, we present a general formalism that allows us to discover decision rules that establish a mapping between easily accessible attributes of a system and its properties. It is shown that fingerprints based on either chemo-structural (compositional and configurational information) or the electronic charge density distribution can be used to make ultra-fast, yet accurate, property predictions. Harnessing such learning paradigms extends recent efforts to systematically explore and mine vast chemical spaces and can significantly accelerate the discovery of new application-specific materials.
@article{pilania_accelerating_2013,
title = {Accelerating materials property predictions using machine learning},
volume = {3},
copyright = {2013 The Author(s)},
issn = {2045-2322},
url = {https://www.nature.com/articles/srep02810},
doi = {10.1038/srep02810},
abstract = {The materials discovery process can be significantly expedited and simplified if we can learn effectively from available knowledge and data. In the present contribution, we show that efficient and accurate prediction of a diverse set of properties of material systems is possible by employing machine (or statistical) learning methods trained on quantum mechanical computations in combination with the notions of chemical similarity. Using a family of one-dimensional chain systems, we present a general formalism that allows us to discover decision rules that establish a mapping between easily accessible attributes of a system and its properties. It is shown that fingerprints based on either chemo-structural (compositional and configurational information) or the electronic charge density distribution can be used to make ultra-fast, yet accurate, property predictions. Harnessing such learning paradigms extends recent efforts to systematically explore and mine vast chemical spaces and can significantly accelerate the discovery of new application-specific materials.},
language = {en},
number = {1},
urldate = {2023-06-15},
journal = {Scientific Reports},
author = {Pilania, Ghanshyam and Wang, Chenchen and Jiang, Xun and Rajasekaran, Sanguthevar and Ramprasad, Ramamurthy},
month = sep,
year = {2013},
note = {Number: 1
Publisher: Nature Publishing Group},
keywords = {Computational methods, Electronic properties and materials, Electronic structure, Polymers},
pages = {2810},
}
Downloads: 0
{"_id":"eCuYTia5sQvjf7zaj","bibbaseid":"pilania-wang-jiang-rajasekaran-ramprasad-acceleratingmaterialspropertypredictionsusingmachinelearning-2013","downloads":0,"creationDate":"2015-09-03T07:18:24.417Z","title":"Accelerating materials property predictions using machine learning","author_short":["Pilania, G.","Wang, C.","Jiang, X.","Rajasekaran, S.","Ramprasad, R."],"year":2013,"bibtype":"article","biburl":"https://bibbase.org/zotero/pranoyr","bibdata":{"bibtype":"article","type":"article","title":"Accelerating materials property predictions using machine learning","volume":"3","copyright":"2013 The Author(s)","issn":"2045-2322","url":"https://www.nature.com/articles/srep02810","doi":"10.1038/srep02810","abstract":"The materials discovery process can be significantly expedited and simplified if we can learn effectively from available knowledge and data. In the present contribution, we show that efficient and accurate prediction of a diverse set of properties of material systems is possible by employing machine (or statistical) learning methods trained on quantum mechanical computations in combination with the notions of chemical similarity. Using a family of one-dimensional chain systems, we present a general formalism that allows us to discover decision rules that establish a mapping between easily accessible attributes of a system and its properties. It is shown that fingerprints based on either chemo-structural (compositional and configurational information) or the electronic charge density distribution can be used to make ultra-fast, yet accurate, property predictions. Harnessing such learning paradigms extends recent efforts to systematically explore and mine vast chemical spaces and can significantly accelerate the discovery of new application-specific materials.","language":"en","number":"1","urldate":"2023-06-15","journal":"Scientific Reports","author":[{"propositions":[],"lastnames":["Pilania"],"firstnames":["Ghanshyam"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Chenchen"],"suffixes":[]},{"propositions":[],"lastnames":["Jiang"],"firstnames":["Xun"],"suffixes":[]},{"propositions":[],"lastnames":["Rajasekaran"],"firstnames":["Sanguthevar"],"suffixes":[]},{"propositions":[],"lastnames":["Ramprasad"],"firstnames":["Ramamurthy"],"suffixes":[]}],"month":"September","year":"2013","note":"Number: 1 Publisher: Nature Publishing Group","keywords":"Computational methods, Electronic properties and materials, Electronic structure, Polymers","pages":"2810","bibtex":"@article{pilania_accelerating_2013,\n\ttitle = {Accelerating materials property predictions using machine learning},\n\tvolume = {3},\n\tcopyright = {2013 The Author(s)},\n\tissn = {2045-2322},\n\turl = {https://www.nature.com/articles/srep02810},\n\tdoi = {10.1038/srep02810},\n\tabstract = {The materials discovery process can be significantly expedited and simplified if we can learn effectively from available knowledge and data. In the present contribution, we show that efficient and accurate prediction of a diverse set of properties of material systems is possible by employing machine (or statistical) learning methods trained on quantum mechanical computations in combination with the notions of chemical similarity. Using a family of one-dimensional chain systems, we present a general formalism that allows us to discover decision rules that establish a mapping between easily accessible attributes of a system and its properties. It is shown that fingerprints based on either chemo-structural (compositional and configurational information) or the electronic charge density distribution can be used to make ultra-fast, yet accurate, property predictions. Harnessing such learning paradigms extends recent efforts to systematically explore and mine vast chemical spaces and can significantly accelerate the discovery of new application-specific materials.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2023-06-15},\n\tjournal = {Scientific Reports},\n\tauthor = {Pilania, Ghanshyam and Wang, Chenchen and Jiang, Xun and Rajasekaran, Sanguthevar and Ramprasad, Ramamurthy},\n\tmonth = sep,\n\tyear = {2013},\n\tnote = {Number: 1\nPublisher: Nature Publishing Group},\n\tkeywords = {Computational methods, Electronic properties and materials, Electronic structure, Polymers},\n\tpages = {2810},\n}\n\n\n\n","author_short":["Pilania, G.","Wang, C.","Jiang, X.","Rajasekaran, S.","Ramprasad, R."],"key":"pilania_accelerating_2013","id":"pilania_accelerating_2013","bibbaseid":"pilania-wang-jiang-rajasekaran-ramprasad-acceleratingmaterialspropertypredictionsusingmachinelearning-2013","role":"author","urls":{"Paper":"https://www.nature.com/articles/srep02810"},"keyword":["Computational methods","Electronic properties and materials","Electronic structure","Polymers"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"search_terms":["accelerating","materials","property","predictions","using","machine","learning","pilania","wang","jiang","rajasekaran","ramprasad"],"keywords":["computational methods","electronic properties and materials","electronic structure","polymers"],"authorIDs":[],"dataSources":["y8en6y5RHukfeLuPH","ybfSxqcjZRxzggkgs"]}